AI 写代码终于不是只管一段，而是能搭整个项目了
以前让 AI 写代码，它只能写一个文件或一个函数，整个项目的结构——哪个模块该放哪、接口怎么连——得人自己搭。Repo0 把这件事反过来：它先不写一行代码，而是用两张图(一张画需求关系、一张画组件依赖)把项目架构画出来，然后像建筑师调平面图一样，反复调整组件边界直到结构合理，最后才让 AI 按这个架构去写代码。在 6 个真实项目上，它比最好的基线方案功能覆盖率高 20 个百分点，通过率高 30 个百分点。它不是你明天就能用的工具，但方向很明确：AI 写软件，从「写段落」进化到「写整本书」，靠的是先想清楚结构再动笔。
📄 原文摘要(英文)
Large language model agents have made substantial progress in code generation, yet most existing systems assume a predefined repository architecture. This assumption does not hold in zero-to-all code generation, where an agent must construct an entire software project directly from natural-language requirements while maintaining a modular repository architecture throughout development. We present Repo0, a continuous structural evolution framework for zero-to-all code generation. Repo0 maintains an explicit architectural state instantiated as a Dual-Directed-Acyclic-Graph (Dual-DAG), consisting of a requirement-level DAG, a component-level DAG, and their alignment relation. Starting from natural-language requirements, it iteratively evolves component boundaries through structural actions guided by modularity metrics until structural convergence, after which the converged architecture guides test-driven development code generation. We evaluate Repo0 on six real-world repositories from RepoCraft using GPT-5 mini and DeepSeek V3.2. Repo0 achieves the highest Functionality Coverage and Pass Rate across all settings. Compared with RPG, the strongest repository-planning baseline, Repo0 improves Functionality Coverage by up to 20.08 percentage points and Pass Rate by up to 29.74 percentage points. Ablation and structural-evolution analyses further demonstrate the importance of the Dual-DAG architectural state, modularity-guided structural evolution, and explicit structural convergence.